Self-play in simulation produces robust driving policies at scale. Demonstrations of such behavior have been made using privileged vectorized observations such as exact poses and velocities, even for ...

One step from real. State-of-the-art one-step generation by matching feature distributions, no online teacher, no adversary, no trajectory.

An official ELLIS Summer School — four intensive days in Barcelona where world-class researchers and the next generation of scientists converge to push the boundaries of perception, world models, end-to-end driving, and beyond.